Search

Purpose: To investigate opinions among healthcare stakeholders whether implementation of the N-of-1 trial approach in clinical practice is a feasible way to optimize evidence-based treatment results for unique patients. Methods: We interviewed clinicians, researchers, and a patient advocate (n = 13) with an interest in or experience with N-of-1 trials on the following topics: experience with N-of-1, measurement, validity and reliability, informally gathered data usability, and influence on physician-patient relationship. Interviews were analysed using qualitative, thematic analysis. Results: The N-of-1 approach has the potential to shift the current healthcare system towards embracing personalized medicine. However, its application in clinical practice carries significant challenges in terms of logistics, time investment and acceptability. New skills will be required from patients and healthcare providers, which may alter the patient-physician relationship. The rise of consumer technology enabling self-measurement may leverage the uptake of N-of-1 approaches in clinical practice. Conclusions: There is a strong belief that the N-of-1 approach has the potential to play a prominent role in transitioning the current healthcare system towards embracing personalized medicine. However, there are many barriers deeply ingrained in our healthcare system that hamper the uptake of the N-of-1 approach, making it momentarily only interesting for research purposes. Highlights: Key findings The potential merits of adopting N-of-1 trials into clinical practice (in terms of efficacy and participation) was acknowledged by all participants. The trade-off between methodological rigidity and practical application for the patient was mentioned by clinicians as an important barrier for the use of N-of-1 trials in clinical practice. There appears to be substantial dissensus on the usefulness of "informal/pragmatic" N-of-1 trials in clinical practice; clinicians appear the strongest advocates for strict methodological rigour. What this adds to what is known Previous research suggests that lack of knowledge by researchers, clinicians, and patients on the topic of N-of-1, operational complexity, and costs are primary barriers for adoption of N-of-1 trials in clinical practice. Our work confirms the abovementioned barriers and adds to this list: the current design of the healthcare system and the lack of consensus on methodological requirements. The Quantified Self movement as well as the advances in the wearable technology were mentioned by (patient)researchers as facilitators for the adoption of N-of-1 methodologies in clinical practice. What is the implication, what should change now Education on N-of-1 trials need to be included in the medical (and thus not only the biomedical sciences) curriculum. The N-of-1 approach might help promote shared decision making in which patient can lead using their own data. Best practices of N-of-1 adoption in clinical practice need to be identified and used as examples to further inform communication between medical stakeholders and policymakers. [ABSTRACT FROM AUTHOR]

Soft bioelectronics have emerged as a promising platform for personalized healthcare, offering improved compatibility with biological tissues. Among various soft materials, hydrogels stand out due to their unique tissue-like properties and multifunctionality. However, the development of hydrogel-based bioelectronics faces three major challenges: (1) achieving a wide range of mechanical properties, from kilopascals to gigapascals, to match diverse tissues from soft brain to stiff tendon; (2) balancing and decoupling various material properties, particularly mechanical and electrical characteristics, and (3) achieving effective implantation and integration with target organs. This review provides a comprehensive overview of recent advancements in hydrogel-based bioelectronics, focusing on strategies to address these challenges. We first explore approaches to tune the mechanical properties of hydrogels, matching them with a wide range of tissues from soft brain tissue to stiff tendons. We then discuss innovative methods to incorporate conductivity into hydrogels while maintaining their mechanical integrity, highlighting recent developments in conductive polymers that show potential in decoupling electrical and mechanical properties. To address the challenge of implantation, we examine emerging concepts in stimuli-responsive hydrogels capable of programmable deformation, enabling targeted attachment and conformability to specific organs. We also categorize and analyze applications of hydrogel-based systems in both wearable and implantable devices, compiling the latest progress in hydrogel bioelectronics at the application level. While significant advancements have been made, integrating multiple functionalities within a single hydrogel-based device remains a considerable challenge. Further research is necessary to develop truly multimodal bioelectronic systems that can seamlessly interface with the human body, ultimately translating these promising technologies into clinical practice. Highlights: Summarizes recent advances in hydrogel bioelectronics for personalized healthcare, focusing on mechanical, electrical, acoustic, and optogenetic coupling. Discusses the latest progress in conductive polymers, particularly PEDOT:PSS, and their potential in decoupling electrical and mechanical properties. Discusses the concept of stimuli-responsive hydrogels that enable programmable deformation for targeted attachment and conformability to specific organs. [ABSTRACT FROM AUTHOR]

Advancements in optoelectronic biointerfaces have revolutionized healthcare by enabling targeted stimulation and monitoring of cells, tissues, and organs. Photostimulation, a key application, offers precise control over biological processes, surpassing traditional modulation methods with increased spatial resolution and reduced invasiveness. This perspective highlights three approaches in non-genetic optoelectronic photostimulation: nanostructured phototransducers for cellular stimulation, micropatterned photoelectrode arrays for tissue stimulation, and thin-film flexible photoelectrodes for multiscale stimulation. Nanostructured phototransducers provide localized stimulation at the cellular or subcellular level, facilitating cellular therapy and regenerative medicine. Micropatterned photoelectrode arrays offer precise tissue stimulation, critical for targeted therapeutic interventions. Thin-film flexible photoelectrodes combine flexibility and biocompatibility for scalable medical applications. Beyond neuromodulation, optoelectronic biointerfaces hold promise in cardiology, oncology, wound healing, and endocrine and respiratory therapies. Future directions include integrating these devices with advanced imaging and feedback systems, developing wireless and biocompatible devices for long-term use, and creating multifunctional devices that combine photostimulation with other therapies. The integration of light and electronics through these biointerfaces paves the way for innovative, less invasive, and more accurate medical treatments, promising a transformative impact on patient care across various medical fields. Highlights: • Non-genetic optoelectronic biointerfaces revolutionize healthcare by enabling precise biological stimulation and monitoring. • Key methods include nanostructured phototransducers, micropatterned arrays, and thin-film flexible electrodes. • Future advancements will integrate imaging, develop wireless devices, and create multifunctional therapies, transforming patient care. [ABSTRACT FROM AUTHOR]

Abstract Polysomnography is the diagnostic gold standard for obstructive sleep apnea-hypopnea syndrome (OSAHS), requiring medical professionals to analyze apnea-hypopnea events from multidimensional data throughout the sleep cycle. This complex process is susceptible to variability based on the clinician’s experience, leading to potential inaccuracies. Existing automatic diagnosis methods often overlook multimodal physiological signals and medical prior knowledge, leading to limited diagnostic capabilities. This study presents a novel heterogeneous graph convolutional fusion network (HeteroGCFNet) leveraging multimodal physiological signals and domain knowledge for automated OSAHS diagnosis. This framework constructs two types of graph representations: physical space graphs, which map the spatial layout of sensors on the human body, and process knowledge graphs which detail the physiological relationships among breathing patterns, oxygen saturation, and vital signals. The framework leverages heterogeneous graph convolutional neural networks to extract both localized and global features from these graphs. Additionally, a multi-head fusion module combines these features into a unified representation for effective classification, enhancing focus on relevant signal characteristics and cross-modal interactions. This study evaluated the proposed framework on a large-scale OSAHS dataset, combined from publicly available sources and data provided by a collaborative university hospital. It demonstrated superior diagnostic performance compared to conventional machine learning models and existing deep learning approaches, effectively integrating domain knowledge with data-driven learning to produce explainable representations and robust generalization capabilities, which can potentially be utilized for clinical use. Code is available at https://github.com/AmbitYuki/HeteroGCFNet .

Polysomnography is the diagnostic gold standard for obstructive sleep apnea-hypopnea syndrome (OSAHS), requiring medical professionals to analyze apnea-hypopnea events from multidimensional data throughout the sleep cycle. This complex process is susceptible to variability based on the clinician’s experience, leading to potential inaccuracies. Existing automatic diagnosis methods often overlook multimodal physiological signals and medical prior knowledge, leading to limited diagnostic capabilities. This study presents a novel heterogeneous graph convolutional fusion network (HeteroGCFNet) leveraging multimodal physiological signals and domain knowledge for automated OSAHS diagnosis. This framework constructs two types of graph representations: physical space graphs, which map the spatial layout of sensors on the human body, and process knowledge graphs which detail the physiological relationships among breathing patterns, oxygen saturation, and vital signals. The framework leverages heterogeneous graph convolutional neural networks to extract both localized and global features from these graphs. Additionally, a multi-head fusion module combines these features into a unified representation for effective classification, enhancing focus on relevant signal characteristics and cross-modal interactions. This study evaluated the proposed framework on a large-scale OSAHS dataset, combined from publicly available sources and data provided by a collaborative university hospital. It demonstrated superior diagnostic performance compared to conventional machine learning models and existing deep learning approaches, effectively integrating domain knowledge with data-driven learning to produce explainable representations and robust generalization capabilities, which can potentially be utilized for clinical use. Code is available at . [ABSTRACT FROM AUTHOR]

Access to healthcare, while globally recognized as a human right, presents significant disparities, particularly in urgent care accessibility and equity within Riyadh's neighborhoods. This study addresses the existing gaps in understanding how disparities in urgent care access can impact the broader goal of personalized healthcare in Riyadh's primary healthcare centers (PHCs). The study aims to examine the equity and accessibility of urgent care services in PHCs across Riyadh, Saudi Arabia, evaluating how these factors contribute to personalized healthcare. We hypothesized that significant differences exist in the accessibility and equity of urgent care services among various Riyadh neighborhoods. We conducted a cross-sectional online survey with 359 participants from diverse Riyadh neighborhoods. Data were collected using a structured questionnaire and analyzed using SPSS Version 23.0 to explore regional differences in urgent care accessibility and perceptions of equity. The study revealed significant regional disparities in urgent care accessibility within Riyadh, Saudi Arabia. Specifically, residents in the Western region reported the highest access and awareness (80.84% availability within 30 minutes), while those in the Eastern region reported the least (76.19% access to healthcare centers). Additionally, 32.6% of the participants were from the Western region, 24.5% from the Eastern region, 21.7% from the Southern region, and 21.2% from the Northern region. A notable preference was found for seeking urgent care in secondary and military hospitals, attributed to perceived better resources and specialist availability. The findings emphasize the need for targeted interventions to enhance PHC capabilities and utilization, ensuring alignment with personalized healthcare principles that cater to specific regional needs and conditions. [ABSTRACT FROM AUTHOR]

AbstractNanotechnology has emerged as a pivotal force in biomedical research, offering groundbreaking solutions for disease treatment and prevention through the integration of nanoscience with biology. This review explores the multifaceted applications of nano-bio interfaces in revolutionizing therapeutic interventions and public health strategies. At the forefront of innovation, nanomaterial-based drug delivery systems demonstrate unparalleled precision and efficacy in targeted drug delivery, minimizing systemic toxicity and maximizing therapeutic outcomes. Furthermore, the development of multifunctional nanoparticles capable of simultaneous drug delivery and diagnostic imaging enables real-time monitoring of treatment responses, heralding a new era of personalized medicine. Nano-bio interfaces also play a crucial role in advancing vaccine development and immunotherapies, with nanoparticle-based vaccine platforms offering enhanced antigen delivery and immune stimulation for robust and durable immune responses against infectious diseases and cancer. In the realm of disease prevention, antimicrobial nanomaterials provide effective strategies for infection control, while nanovaccines and prophylactic drug delivery systems offer tailored solutions for mitigating the spread of infectious agents. Through a comprehensive exploration of these pioneering approaches, this review, we believe, highlights the transformative potential of nano-bio interfaces in reshaping the landscape of disease treatment and prevention. [ABSTRACT FROM AUTHOR]

The global healthcare market is expanding, with a particular focus on personalized care for individuals who are unable to leave their homes due to the COVID-19 pandemic. However, the implementation of personalized care is challenging due to the need for additional devices, such as smartwatches and wearable trackers. This study aims to develop a human body simulation that predicts and visualizes an individual's 3D body changes based on 2D images taken by a portable device. The simulation proposed in this study uses semantic segmentation and image-based reconstruction techniques to preprocess 2D images and construct 3D body models. It also considers the user's exercise plan to enable the visualization of 3D body changes. The proposed simulation was developed based on human-in-the-loop experimental results and literature data. The experiment shows that there is no statistical difference between the simulated body and actual anthropometric measurement with a p-value of 0.3483 in the paired t-test. The proposed simulation provides an accurate and efficient estimation of the human body in a 3D environment, without the need for expensive equipment such as a 3D scanner or scanning uniform, unlike the existing anthropometry approach. This can promote preventive treatment for individuals who lack access to healthcare. [ABSTRACT FROM AUTHOR]

The National Institute of Health Stroke Scale (NIHSS) is used worldwide to classify stroke severity as 'mild', 'moderate', or 'severe' based on neurological impairment. Yet, stroke survivors argue that the classification of 'mild' does not represent the holistic experience and impact of stroke on their daily lives. In this observational cohort study, we aimed to identify different types of impairment profiles among stroke survivors classified as 'mild'. We used survivors of mild stroke' data from the START longitudinal stroke cohort (n = 73), with measures related to sensorimotor, cognition, depression, functional disability, physical activity, work, and social adjustment over 12 months. Given the multisource, multigranular, and unlabeled nature of the data, we utilized a structure-adapting, unsupervised machine learning approach, the growing self-organizing map (GSOM) algorithm, to generate distinct clinical profiles. These diverse impairment profiles revealed that survivors of mild stroke experience varying degrees of impairment and impact (cognitive, depression, physical activity, work/social adjustment) at different time points, despite the uniformity implied by their NIHSS-classified 'mild' stroke. This emphasizes the necessity of creating a holistic and more comprehensive representation of survivors of mild stroke' needs over the first year after stroke to improve rehabilitation and poststroke care. [ABSTRACT FROM AUTHOR]

Diabetes is a global epidemic with severe consequences for individuals and healthcare systems. While early and personalized prediction can significantly improve outcomes, traditional centralized prediction models suffer from privacy risks and limited data diversity. This paper introduces a novel framework that integrates blockchain and federated learning to address these challenges. Blockchain provides a secure, decentralized foundation for data management, access control, and auditability. Federated learning enables model training on distributed datasets without compromising patient privacy. This collaborative approach facilitates the development of more robust and personalized diabetes prediction models, leveraging the combined data resources of multiple healthcare institutions. We have performed extensive evaluation experiments and security analyses. The results demonstrate good performance while significantly enhancing privacy and security compared to centralized approaches. Our framework offers a promising solution for the ethical and effective use of healthcare data in diabetes prediction. [ABSTRACT FROM AUTHOR]

Purpose To investigate opinions among healthcare stakeholders whether implementation of the N-of-1 trial approach in clinical practice is a feasible way to optimize evidence-based treatment results for unique patients. Methods We interviewed clinicians, researchers, and a patient advocate (n = 13) with an interest in or experience with N-of-1 trials on the following topics: experience with N-of-1, measurement, validity and reliability, informally gathered data usability, and influence on physician-patient relationship. Interviews were analysed using qualitative, thematic analysis. Results The N-of-1 approach has the potential to shift the current healthcare system towards embracing personalized medicine. However, its application in clinical practice carries significant challenges in terms of logistics, time investment and acceptability. New skills will be required from patients and healthcare providers, which may alter the patient-physician relationship. The rise of consumer technology enabling self-measurement may leverage the uptake of N-of-1 approaches in clinical practice. Conclusions There is a strong belief that the N-of-1 approach has the potential to play a prominent role in transitioning the current healthcare system towards embracing personalized medicine. However, there are many barriers deeply ingrained in our healthcare system that hamper the uptake of the N-of-1 approach, making it momentarily only interesting for research purposes.

Patient-Centric Knowledge Graphs (PCKGs) represent an important shift in healthcare that focuses on individualized patient care by mapping the patient’s health information holistically and multi-dimensionally. PCKGs integrate various types of health data to provide healthcare professionals with a comprehensive understanding of a patient’s health, enabling more personalized and effective care. This literature review explores the methodologies, challenges, and opportunities associated with PCKGs, focusing on their role in integrating disparate healthcare data and enhancing patient care through a unified health perspective. In addition, this review also discusses the complexities of PCKG development, including ontology design, data integration techniques, knowledge extraction, and structured representation of knowledge. It highlights advanced techniques such as reasoning, semantic search, and inference mechanisms essential in constructing and evaluating PCKGs for actionable healthcare insights. We further explore the practical applications of PCKGs in personalized medicine, emphasizing their significance in improving disease prediction and formulating effective treatment plans. Overall, this review provides a foundational perspective on the current state-of-the-art and best practices of PCKGs, guiding future research and applications in this dynamic field.

Abstract An ever-increasing amount of data on a person’s daily functioning is being collected, which holds information to revolutionize person-centered healthcare. However, the full potential of data on daily functioning cannot yet be exploited as it is mostly stored in an unstructured and inaccessible manner. The integration of these data, and thereby expedited knowledge discovery, is possible by the introduction of functionomics as a complementary ‘omics’ initiative, embracing the advances in data science. Functionomics is the study of high-throughput data on a person’s daily functioning, that can be operationalized with the International Classification of Functioning, Disability and Health (ICF). A prerequisite for making functionomics operational are the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper illustrates a step by step application of the FAIR principles for making functionomics data machine readable and accessible, under strictly certified conditions, in a practical example. Establishing more FAIR functionomics data repositories, analyzed using a federated data infrastructure, enables new knowledge generation to improve health and person-centered healthcare. Together, as one allied health and healthcare research community, we need to consider to take up the here proposed methods.

An ever-increasing amount of data on a person's daily functioning is being collected, which holds information to revolutionize person-centered healthcare. However, the full potential of data on daily functioning cannot yet be exploited as it is mostly stored in an unstructured and inaccessible manner. The integration of these data, and thereby expedited knowledge discovery, is possible by the introduction of functionomics as a complementary 'omics' initiative, embracing the advances in data science. Functionomics is the study of high-throughput data on a person's daily functioning, that can be operationalized with the International Classification of Functioning, Disability and Health (ICF). A prerequisite for making functionomics operational are the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper illustrates a step by step application of the FAIR principles for making functionomics data machine readable and accessible, under strictly certified conditions, in a practical example. Establishing more FAIR functionomics data repositories, analyzed using a federated data infrastructure, enables new knowledge generation to improve health and person-centered healthcare. Together, as one allied health and healthcare research community, we need to consider to take up the here proposed methods. [ABSTRACT FROM AUTHOR]

This concise analysis examines the application of AI, particularly chatbots and natural language processing (NLP), to enhance maternal-infant healthcare in Spain and Brazil, where maternal mortality rates are significantly different, as well as birth rate and reproductive health planning or birth control. The application will be preliminary tested in complex situations regarding these two use cases. It highlights the integration of disruptive technologies into prenatal care, emphasizing the role of AI in facilitating personalized healthcare and self-management through data acquisition on health parameters, such as weight gain, blood pressure, incontinence, mental health, nutrition and physical activity. The study reflects on the impact of digital tools in optimizing patient engagement and early diagnosis of alarm symptoms, showcasing the potential of m-Health applications in transforming care practices and contributing to attaining Global Health Objectives for 2030. [ABSTRACT FROM AUTHOR]

Acute and infected wounds resulting from accidents, battlefield trauma, or surgical interventions have become a global healthcare burden due to the complex bacterial infection environment. However, conventional gauze dressings present insufficient contact with irregular wounds and lack antibacterial activity against multi‐drug‐resistant bacteria. In this study, we develop in situ nanofibrous dressings tailored to fit wounds of various shapes and sizes while providing nanoscale comfort and excellent antibacterial properties. Our approach involves the fabrication of these dressings using a handheld electrospinning device that allows for the direct deposition of nanofiber dressings onto specific irregular wound sites, resulting in perfect conformal wound closure without any mismatch in 2 min. The nanofibrous dressings are loaded with multi‐armed antibiotics that exhibit outstanding antibacterial activity against Staphylococcus aureus (S. aureus) and methicillin‐resistant S. aureus. Compared to conventional vancomycin, this in situ nanofibrous dressing shows great antibacterial performance against up to 98% of multi‐drug‐resistant bacteria. In vitro and in vivo experiments demonstrate the ability of in situ nanofibrous dressings to prevent multi‐drug‐resistant bacterial infection, greatly alleviate inflammation, and promote wound healing. Our findings highlight the potential of these personalized nanofibrous dressings for clinical applications, including emergency, accident, and surgical healthcare treatment. [ABSTRACT FROM AUTHOR]

Recent advancements in polymer-assisted layer-by-layer (LbL) fabrication have revolutionized the development of wearable sensors for health monitoring. LbL self-assembly has emerged as a powerful and versatile technique for creating conformal, flexible, and multi-functional films on various substrates, making it particularly suitable for fabricating wearable sensors. The incorporation of polymers, both natural and synthetic, has played a crucial role in enhancing the performance, stability, and biocompatibility of these sensors. This review provides a comprehensive overview of the principles of LbL self-assembly, the role of polymers in sensor fabrication, and the various types of LbL-fabricated wearable sensors for physical, chemical, and biological sensing. The applications of these sensors in continuous health monitoring, disease diagnosis, and management are discussed in detail, highlighting their potential to revolutionize personalized healthcare. Despite significant progress, challenges related to long-term stability, biocompatibility, data acquisition, and large-scale manufacturing are still to be addressed, providing insights into future research directions. With continued advancements in polymer-assisted LbL fabrication and related fields, wearable sensors are poised to improve the quality of life for individuals worldwide. [ABSTRACT FROM AUTHOR]

In the dynamic landscape of healthcare, Digital Twin (DT) technology has emerged as a transformative force, holding the promise of revolutionizing patient care and industry practices. This article surveys the literature over the period 2020 to 2023 on a comprehensive exploration of DT in healthcare, elucidating its roles, benefits, and implications for smart personalized healthcare. The study addresses fundamental questions concerning the transformative potential of DT, investigating its varied roles and benefits in healthcare, its revolutionary impact on the industry, and the essential requirements for crafting a DT system tailored to the demands of smart personalized healthcare. The research further unveils the key layers necessary for implementing a DT smart healthcare system, examining potential applications that extend from diagnostics to treatment strategies. Methodologically, the paper navigates through different model discussions, providing a structured approach to understanding the implementation of DT in healthcare. Despite the transformative potential, the research delves into the limitations and challenges faced by DT technology, offering a balanced perspective on its current state. In conclusion, the paper synthesizes key findings, outlines methodologies, discusses challenges, and sets the stage for future research, presenting a holistic overview of the potential, pitfalls, and pathways for integrating DT in the healthcare industry.

Genetic testing is key in modern healthcare, particularly for monogenic disorders such as familial hypercholesterolemia. This Tohoku Medical Megabank Project study explored the impact of first-degree relatives' dyslipidemia history on individual responses to familial hypercholesterolemia genomic results. Involving 214 participants and using Japan's 3.5KJPN genome reference panel, the study assessed preferences and intentions regarding familial hypercholesterolemia genetic testing results. The data revealed a significant inclination among participants with a family history of dyslipidemia to share their genetic test results, with more than 80% of participants intending to share positive results with their partners and children and 98.1% acknowledging the usefulness of positive results for personal health management. The study underscores the importance of family health history in genetic-testing perceptions, highlighting the need for family-centered approaches in genetic counseling and healthcare. Notable study limitations include the regional scope and reliance on questionnaire data. The study results emphasize the association between family health history and genetic-testing attitudes and decisions. [ABSTRACT FROM AUTHOR]

Electronic textiles (e‐textiles) have emerged as a revolutionary solution for personalized healthcare, enabling the continuous collection and communication of diverse physiological parameters when seamlessly integrated with the human body. Among various methods employed to create wearable e‐textiles, printing offers unparalleled flexibility and comfort, seamlessly integrating wearables into garments. This has spurred growing research interest in printed e‐textiles, due to their vast design versatility, material options, fabrication techniques, and wide‐ranging applications. Here, a comprehensive overview of the crucial considerations in fabricating printed e‐textiles is provided, encompassing the selection of conductive materials and substrates, as well as the essential pre‐ and post‐treatments involved. Furthermore, the diverse printing techniques and the specific requirements are discussed, highlighting the advantages and limitations of each method. Additionally, the multitude of wearable applications made possible by printed e‐textiles is explored, such as their integration as various sensors, supercapacitors, and heated garments. Finally, a forward‐looking perspective is provided, discussing future prospects and emerging trends in the realm of printed wearable e‐textiles. As advancements in materials science, printing technologies, and design innovation continue to unfold, the transformative potential of printed e‐textiles in healthcare and beyond is poised to revolutionize the way wearable technology interacts and benefits. [ABSTRACT FROM AUTHOR]

This paper deals with the development of an approach for diabetes classification harnessing Convolutional-Neural-network (CNN) and a Long-Short-Term-Memory (LSTM) model. The proposed method harnesses the strengths of LSTM and CNN architectures to effectively capture sequential patterns and extract meaningful features from the input data. A comprehensive dataset containing relevant features for diabetes patients is used to train and evaluate the classifiers. Evaluation metrics such as kappa score, F1-score, accuracy, precision, and recall are employed in ordre to assess the performance of each model. The results demonstrate that the CNNLSTM model outperforms other models, including Logistic Regression, Random Forest, SVM, and KNN, achieving an impressive accuracy of 97%. These findings shed light on the effectiveness of the proposed approach in accurately classifying diabetes, resulting in significant advancement in diabetes diagnosis and treatment and opening up exciting possibilities for personalized healthcare. [ABSTRACT FROM AUTHOR]

Abstract Acute and infected wounds resulting from accidents, battlefield trauma, or surgical interventions have become a global healthcare burden due to the complex bacterial infection environment. However, conventional gauze dressings present insufficient contact with irregular wounds and lack antibacterial activity against multi‐drug‐resistant bacteria. In this study, we develop in situ nanofibrous dressings tailored to fit wounds of various shapes and sizes while providing nanoscale comfort and excellent antibacterial properties. Our approach involves the fabrication of these dressings using a handheld electrospinning device that allows for the direct deposition of nanofiber dressings onto specific irregular wound sites, resulting in perfect conformal wound closure without any mismatch in 2 min. The nanofibrous dressings are loaded with multi‐armed antibiotics that exhibit outstanding antibacterial activity against Staphylococcus aureus (S. aureus) and methicillin‐resistant S. aureus. Compared to conventional vancomycin, this in situ nanofibrous dressing shows great antibacterial performance against up to 98% of multi‐drug‐resistant bacteria. In vitro and in vivo experiments demonstrate the ability of in situ nanofibrous dressings to prevent multi‐drug‐resistant bacterial infection, greatly alleviate inflammation, and promote wound healing. Our findings highlight the potential of these personalized nanofibrous dressings for clinical applications, including emergency, accident, and surgical healthcare treatment.

The global healthcare market is expanding, with a particular focus on personalized care for individuals who are unable to leave their homes due to the COVID-19 pandemic. However, the implementation of personalized care is challenging due to the need for additional devices, such as smartwatches and wearable trackers. This study aims to develop a human body simulation that predicts and visualizes an individual’s 3D body changes based on 2D images taken by a portable device. The simulation proposed in this study uses semantic segmentation and image-based reconstruction techniques to preprocess 2D images and construct 3D body models. It also considers the user’s exercise plan to enable the visualization of 3D body changes. The proposed simulation was developed based on human-in-the-loop experimental results and literature data. The experiment shows that there is no statistical difference between the simulated body and actual anthropometric measurement with a p-value of 0.3483 in the paired t-test. The proposed simulation provides an accurate and efficient estimation of the human body in a 3D environment, without the need for expensive equipment such as a 3D scanner or scanning uniform, unlike the existing anthropometry approach. This can promote preventive treatment for individuals who lack access to healthcare.

Diabetes is a global epidemic with severe consequences for individuals and healthcare systems. While early and personalized prediction can significantly improve outcomes, traditional centralized prediction models suffer from privacy risks and limited data diversity. This paper introduces a novel framework that integrates blockchain and federated learning to address these challenges. Blockchain provides a secure, decentralized foundation for data management, access control, and auditability. Federated learning enables model training on distributed datasets without compromising patient privacy. This collaborative approach facilitates the development of more robust and personalized diabetes prediction models, leveraging the combined data resources of multiple healthcare institutions. We have performed extensive evaluation experiments and security analyses. The results demonstrate good performance while significantly enhancing privacy and security compared to centralized approaches. Our framework offers a promising solution for the ethical and effective use of healthcare data in diabetes prediction.

The National Institute of Health Stroke Scale (NIHSS) is used worldwide to classify stroke severity as ‘mild’, ‘moderate’, or ‘severe’ based on neurological impairment. Yet, stroke survivors argue that the classification of ‘mild’ does not represent the holistic experience and impact of stroke on their daily lives. In this observational cohort study, we aimed to identify different types of impairment profiles among stroke survivors classified as ‘mild’. We used survivors of mild stroke’ data from the START longitudinal stroke cohort (n = 73), with measures related to sensorimotor, cognition, depression, functional disability, physical activity, work, and social adjustment over 12 months. Given the multisource, multigranular, and unlabeled nature of the data, we utilized a structure-adapting, unsupervised machine learning approach, the growing self-organizing map (GSOM) algorithm, to generate distinct clinical profiles. These diverse impairment profiles revealed that survivors of mild stroke experience varying degrees of impairment and impact (cognitive, depression, physical activity, work/social adjustment) at different time points, despite the uniformity implied by their NIHSS-classified ‘mild’ stroke. This emphasizes the necessity of creating a holistic and more comprehensive representation of survivors of mild stroke’ needs over the first year after stroke to improve rehabilitation and poststroke care.

Physiological monitoring sensors have been critical in diagnosing and improving the healthcare industry over the past 30 years, despite various limitations regarding providing differences in signal outputs in response to the changes in the user's body. Four-dimensional (4D) printing has been established in less than a decade; therefore, it currently offers limited resources and knowledge. Still, the technique paves the way for novel platforms in today's ever-growing technologies. This innovative paradigm of 4D printing physiological monitoring sensors aspires to provide real-time and continuous diagnoses. In this perspective, we cover the advancements currently available in the 4D printing industry that has arisen in the last septennium, focusing on the overview of 4D printing, its history, and both wearable and implantable physiological sensing solutions. Finally, we explore the current challenges faced in this field, translational research, and its future prospects. All of these aims highlight key areas of attention that can be applied by future researchers to fully transform 4D printed physiological monitoring sensors into more viable medical products.

Wearable bioelectronics for continuous and reliable pulse wave monitoring against body motion and perspiration remains a great challenge and highly desired. Here, a low-cost, lightweight, and mechanically durable textile triboelectric sensor that can convert subtle skin deformation caused by arterial pulsatility into electricity for high-fidelity and continuous pulse waveform monitoring in an ambulatory and sweaty setting is developed. The sensor holds a signal-to-noise ratio of 23.3 dB, a response time of 40 ms, and a sensitivity of 0.21 µA kPa-1 . With the assistance of machine learning algorithms, the textile triboelectric sensor can continuously and precisely measure systolic and diastolic pressure, and the accuracy is validated via a commercial blood pressure cuff at the hospital. Additionally, a customized cellphone application (APP) based on built-in algorithm is developed for one-click health data sharing and data-driven cardiovascular diagnosis. The textile triboelectric sensor enabled wireless biomonitoring system is expected to offer a practical paradigm for continuous and personalized cardiovascular system characterization in the era of the Internet of Things.

In the era of big data, artificial intelligence (AI) algorithms have the potential to revolutionize healthcare by improving patient outcomes and reducing healthcare costs. AI algorithms have frequently been used in health care for predictive modelling, image analysis and drug discovery. Moreover, as a recommender system, these algorithms have shown promising impacts on personalized healthcare provision. A recommender system learns the behaviour of the user and predicts their current preferences (recommends) based on their previous preferences. Implementing AI as a recommender system improves this prediction accuracy and solves cold start and data sparsity problems. However, most of the methods and algorithms are tested in a simulated setting which cannot recapitulate the influencing factors of the real world. This review article systematically reviews prevailing methodologies in recommender systems and discusses the AI algorithms as recommender systems specifically in the field of healthcare. It also provides discussion around the most cutting-edge academic and practical contributions present in the literature, identifies performance evaluation matrices, challenges in the implementation of AI as a recommender system, and acceptance of AI-based recommender systems by clinicians. The findings of this article direct researchers and professionals to comprehend currently developed recommender systems and the future of medical devices integrated with real-time recommender systems for personalized healthcare.

Abstract Electronic textiles (e‐textiles) have emerged as a revolutionary solution for personalized healthcare, enabling the continuous collection and communication of diverse physiological parameters when seamlessly integrated with the human body. Among various methods employed to create wearable e‐textiles, printing offers unparalleled flexibility and comfort, seamlessly integrating wearables into garments. This has spurred growing research interest in printed e‐textiles, due to their vast design versatility, material options, fabrication techniques, and wide‐ranging applications. Here, a comprehensive overview of the crucial considerations in fabricating printed e‐textiles is provided, encompassing the selection of conductive materials and substrates, as well as the essential pre‐ and post‐treatments involved. Furthermore, the diverse printing techniques and the specific requirements are discussed, highlighting the advantages and limitations of each method. Additionally, the multitude of wearable applications made possible by printed e‐textiles is explored, such as their integration as various sensors, supercapacitors, and heated garments. Finally, a forward‐looking perspective is provided, discussing future prospects and emerging trends in the realm of printed wearable e‐textiles. As advancements in materials science, printing technologies, and design innovation continue to unfold, the transformative potential of printed e‐textiles in healthcare and beyond is poised to revolutionize the way wearable technology interacts and benefits.

The diagnostic process for psychiatric conditions is guided by the Diagnostic and Statistical Manual of Mental Disorders (DSM) in North America. Revisions of the DSM over the years have led to lowered diagnostic thresholds across the board, incurring increased rates of both misdiagnosis and over-diagnosis. Coupled with stigma, this ambiguity and lack of consistency exacerbates the challenges that clinicians and scientists face in the clinical assessment and research of mood disorders such as Major Depressive Disorder (MDD). While current efforts to characterize MDD have largely focused on qualitative approaches, the broad variations in physiological traits, such as those found in the gut, suggest the immense potential of using biomarkers to provide a quantitative and objective assessment. Here, we propose the development of a probiotic Escherichia coli (E. coli) multi-input ingestible biosensor for the characterization of key gut metabolites implicated in MDD. DNA writing with CRISPR based editors allows for the molecular recording of signals while riboflavin detection acts as a means to establish temporal and spatial specificity for the large intestine. We test the feasibility of this approach through kinetic modeling of the system which demonstrates targeted sensing and robust recording of metabolites within the large intestine in a time-and dose- dependent manner. Additionally, a post-hoc normalization model successfully controlled for confounding factors such as individual variation in riboflavin concentrations, producing a linear relationship between actual and predicted metabolite concentrations. We also highlight indole, butyrate, tetrahydrofolate, hydrogen peroxide, and tetrathionate as key gut metabolites that have the potential to direct our proposed biosensor specifically for MDD. Ultimately, our proposed biosensor has the potential to allow for a greater understanding of disease pathophysiology, assessment, and treatment response for many mood disorders. [ABSTRACT FROM AUTHOR]

Predicting the severity of an illness is crucial in intensive care units (ICUs) if a patient's life is to be saved. The existing prediction methods often fail to provide sufficient evidence for time-critical decisions required in dynamic and changing ICU environments. In this research, a new method called MM-RNN (multi-task memory-fused recurrent neural network) was developed to predict the severity of illnesses in intensive care units (ICUs). MM-RNN aims to address this issue by not only predicting illness severity but also generating an evidence-based explanation of how the prediction was made. The architecture of MM-RNN consists of task-specific phased LSTMs and a delta memory network that captures asynchronous feature correlations within and between multiple organ systems. The multi-task nature of MM-RNN allows it to provide an evidence-based explanation of its predictions, along with illness severity scores and a heatmap of the patient's changing condition. The results of comparison with state-of-the-art methods on real-world clinical data show that MM-RNN delivers more accurate predictions of illness severity with the added benefit of providing evidence-based justifications. [ABSTRACT FROM AUTHOR]